Evaluation of partial discharge measurement by expert systems

Expert systems with the elements of artificial intelligence are the best solution for the evaluation of measured data from the diagnostic measurements and for the estimation of behavior of the insulation system in future operation. Several rule-based expert systems for the diagnostics of high voltage insulation systems have been developed at the Czech Technical University in Prague in the collaboration with other top diagnostic workplaces of the Czech Republic. The complex system for the evaluation of partial discharge (PD) measurement has been developed. Two parallel expert systems work in this complex evaluating system: a rule-based expert system performs an amplitude analysis of PD-impulses for determining the damage of the insulation system, and a neuron network is used for the recognition of PD-patterns (a phase analysis of PD-impulses) to determine the kind of PD-activity and location of the source of PD-activity.